INDEX
Explanations
references to filmmakers and film industry statistics
New Auto-Interp
Negative Logits
365
-0.19
immel
-0.15
779
-0.15
adol
-0.15
trak
-0.14
apk
-0.14
ovy
-0.14
erne
-0.14
erece
-0.14
inja
-0.14
POSITIVE LOGITS
stub
0.17
antan
0.15
Rat
0.14
Vega
0.14
Hanna
0.13
cir
0.13
×IJ
0.13
eki
0.13
agar
0.13
FromBody
0.13
Activations Density 0.018%